1.tensorflow / tensorflow
An Open Source Machine Learning Framework for Everyone
+5,122 stars
from 196,190 · score 8.54
Trending repositories
Ranked by Attention Score: stars gained over the last 90 complete days
1–100 of 111 by Attention Score · Aug 7, 2026 – Nov 4, 2026 (UTC)
2.ggml-org / whisper.cpp
Port of OpenAI's Whisper model in C/C++
+2,523 stars
from 52,407 · score 7.83
3.k2-fsa / sherpa-onnx
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages
+1,801 stars
from 13,941 · score 7.50
4.tesseract-ocr / tesseract
Tesseract Open Source OCR Engine (main repository)
- tesseract
- tesseract-ocr
- ocr
- lstm
- machine-learning
- ocr-engine
- +1 more
+1,765 stars
from 75,579 · score 7.48
5.HIllya51 / LunaTranslator
TranslatedVisual Novel Translator
- galgame
- visual-novel
- translator
- reverse-engineering
- ocr
+1,452 stars
from 12,568 · score 7.28
6.opencv / opencv
Open Source Computer Vision Library
+1,398 stars
from 90,057 · score 7.24
+1,294 stars
from 27,765 · score 7.17
8.mozilla-ai / llamafile
Distribute and run LLMs with a single file.
- cross-platform
- gguf
- llama-cpp
- local-ai
- local-inference
- local-llm
- +3 more
+1,186 stars
from 25,380 · score 7.08
9.google-ai-edge / mediapipe
Cross-platform, customizable ML solutions for live and streaming media.
- mediapipe
- c-plus-plus
- computer-vision
- deep-learning
- android
- video-processing
- +11 more
+1,132 stars
from 36,420 · score 7.03
10.microsoft / onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
- deep-learning
- onnx
- neural-networks
- machine-learning
- ai-framework
- hardware-acceleration
- +3 more
+1,001 stars
from 21,225 · score 6.91
11.colmap / colmap
COLMAP - Structure-from-Motion and Multi-View Stereo
- structure-from-motion
- multi-view-stereo
- reconstruction
- geometry
- computer-vision
+774 stars
from 12,377 · score 6.65
12.alibaba / MNN
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.
- mnn
- convolution
- vulkan
- embedded-devices
- winograd-algorithm
- machine-learning
- +5 more
+589 stars
from 15,763 · score 6.38
13.openvinotoolkit / openvino
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
- inference
- deep-learning
- openvino
- ai
- computer-vision
- diffusion-models
- +13 more
+539 stars
from 10,574 · score 6.29
+506 stars
from 15,073 · score 6.23
15.Tencent / ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
- inference
- high-preformance
- simd
- arm-neon
- deep-learning
- artificial-intelligence
- +14 more
+426 stars
from 23,596 · score 6.06
16.dmlc / xgboost
Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow
- gbdt
- gbrt
- gbm
- distributed-systems
- xgboost
- machine-learning
+357 stars
from 28,586 · score 5.88
17.lightgbm-org / LightGBM
A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.
- gbdt
- gbm
- machine-learning
- data-mining
- distributed
- lightgbm
- +7 more
+327 stars
from 18,623 · score 5.79
18.CMU-Perceptual-Computing-Lab / openpose
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
- openpose
- computer-vision
- machine-learning
- cpp
- caffe
- opencv
- +14 more
+281 stars
from 34,270 · score 5.64
19.NVIDIA / nccl
Optimized primitives for collective multi-GPU communication
- communications
- cpp
- cuda
- deep-learning
- gpu
- nvidia
+273 stars
from 4,938 · score 5.61
20.NVIDIA / TensorRT
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
- tensorrt
- nvidia
- deep-learning
- inference
- gpu-acceleration
+231 stars
from 13,199 · score 5.45
21.RunanywhereAI / runanywhere-sdks
Production ready toolkit to run AI locally
+203 stars
from 10,130 · score 5.32
22.google / sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
- neural-machine-translation
- natural-language-processing
- word-segmentation
+182 stars
from 11,983 · score 5.21
23.catboost / catboost
A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.
- machine-learning
- decision-trees
- gradient-boosting
- gbm
- gbdt
- python
- +12 more
+164 stars
from 9,029 · score 5.11
24.mkiol / dsnote
Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation.
- asr
- sailfishos
- stt
- tts
- flatpak-applications
- linux-desktop
- +9 more
+160 stars
from 1,549 · score 5.08
25.PaddlePaddle / Paddle
TranslatedPArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice (Core framework of 'PaddlePaddle' (飞桨, Feijiang), for deep learning & machine learning: high-performance single-machine and distributed training, and cross-platform deployment)
- paddlepaddle
- deep-learning
- scalability
- machine-learning
- neural-network
- python
- +2 more
+155 stars
from 23,979 · score 5.05
+146 stars
from 2,581 · score 4.99
27.PointCloudLibrary / pcl
Point Cloud Library (PCL)
- pcl
- c-plus-plus
- cpp
- pointcloud
- computer-vision
- point-cloud
+138 stars
from 11,066 · score 4.93
28.Const-me / Whisper
High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model
+136 stars
from 10,567 · score 4.92
29.raulmur / ORB_SLAM2
Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities
+90 stars
from 10,181 · score 4.51
30.rhasspy / piperArchived
A fast, local neural text to speech system
- speech-synthesis
- text-to-speech
- tts
+84 stars
from 11,231 · score 4.44
31.interpretml / interpret
Fit interpretable models. Explain blackbox machine learning.
- machine-learning
- interpretability
- gradient-boosting
- blackbox
- scikit-learn
- xai
- +13 more
+82 stars
from 6,894 · score 4.42
+80 stars
from 10,146 · score 4.39
33.uxlfoundation / oneDNN
Open-source library of optimized deep learning operations (matmul, convolution, attention) for CPUs (x64, AArch64, RISC-V) and Intel GPUs. Used by PyTorch, TensorFlow, OpenVINO, and ONNX Runtime.
- onednn
- oneapi
- performance
- cpp
- x64
- aarch64
- +14 more
+69 stars
from 4,019 · score 4.25
34.davisking / dlib
A toolkit for making real world machine learning and data analysis applications in C++
- machine-learning
- deep-learning
- c-plus-plus
- python
- computer-vision
- machine-learning-library
- +1 more
+65 stars
from 14,403 · score 4.19
35.ShiqiYu / libfacedetection
An open source library for face detection in images. The face detection speed can reach 1000FPS.
- face-detection
- cnn
- arm
+64 stars
from 12,747 · score 4.17
36.alicevision / AliceVision
3D Computer Vision Framework
- computer-vision
- 3d-reconstruction
- photogrammetry
- structure-from-motion
- camera-tracking
- multiview-stereo
- +7 more
+64 stars
from 3,463 · score 4.17
37.BVLC / caffe
Caffe: a fast open framework for deep learning.
+62 stars
from 34,492 · score 4.14
38.activeloopai / deeplake
Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.
- deep-learning
- pytorch
- ai
- mlops
- computer-vision
- datalake
- +13 more
+62 stars
from 9,202 · score 4.14
+58 stars
from 11,421 · score 4.08
40.Farama-Foundation / ViZDoom
Reinforcement Learning environments based on the 1993 game Doom :godmode:
- deep-learning
- reinforcement-learning
- python
- vizdoom
- doom
- examples
- +2 more
+56 stars
from 2,053 · score 4.04
41.VowpalWabbit / vowpal_wabbit
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.
- c-plus-plus
- machine-learning
- online-learning
- contextual-bandits
- reinforcement-learning
- active-learning
- +2 more
+53 stars
from 8,680 · score 3.99
+52 stars
from 1,393 · score 3.97
43.DayBreak-u / chineseocr_lite
TranslatedUltra-lightweight Chinese OCR, supports vertical text recognition, supports ncnn, mnn, and tnn inference (dbnet (1.8M) + crnn (2.5M) + anglenet (378KB)), total model size only 4.7M
+50 stars
from 12,304 · score 3.93
44.mlpack / mlpack
mlpack: a fast, header-only C++ machine learning library
- machine-learning-library
- c-plus-plus
- deep-learning
- nearest-neighbor-search
- regression
- machine-learning
- +1 more
+46 stars
from 5,676 · score 3.85
45.sail-sg / envpool
C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.
- reinforcement-learning
- parallel-processing
- cpp17
- pybind11
- reinforcement-learning-environments
- threadpool
- +10 more
+43 stars
from 1,490 · score 3.78
46.mozilla / DeepSpeechArchived
DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
+41 stars
from 26,731 · score 3.74
47.IvanMurzak / Unreal-MCP
AI Game Developer for Unreal Engine — MCP plugin (C++ editor plugin + .NET bridge), unreal-cli, connects Unreal Editor to AI agents via ai-game.dev or a local MCP server
- ai
- ai-tools
- gamedev
- mcp
- mcp-server
- unreal
- +14 more
+35 stars
from 22 · score 3.58
48.hjwdzh / QuadriFlow
QuadriFlow: A Scalable and Robust Method for Quadrangulation
- quadriflow
- quad
- remeshing
- quadrangulation
- geometry
+34 stars
from 848 · score 3.56
49.liuliu / ccv
C-based/Cached/Core Computer Vision Library, A Modern Computer Vision Library
+28 stars
from 7,224 · score 3.37
50.microsoft / CNTKArchived
Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit
- cognitive-toolkit
- cntk
- deep-learning
- machine-learning
- deep-neural-networks
- neural-network
- +5 more
+26 stars
from 17,557 · score 3.30
51.flashlight / flashlight
A C++ standalone library for machine learning
- flashlight
- machine-learning
- autograd
- cpp
- deep-learning
- neural-network
- +1 more
+26 stars
from 5,453 · score 3.30
+26 stars
from 588 · score 3.30
53.leela-zero / leela-zero
Go engine with no human-provided knowledge, modeled after the AlphaGo Zero paper.
+20 stars
from 5,573 · score 3.04
+20 stars
from 2,429 · score 3.04
55.ZigRazor / CXXGraph
Header-Only C++ Library for Graph Representation and Algorithms
- search-algorithm
- dijkstra-algorithm
- graph
- graph-algorithms
- graph-theory-algorithms
- graph-analysis
- +14 more
+19 stars
from 719 · score 3.00
+15 stars
from 2,718 · score 2.77
57.ankitdhall / lidar_camera_calibration
ROS package to find a rigid-body transformation between a LiDAR and a camera for "LiDAR-Camera Calibration using 3D-3D Point correspondences"
+15 stars
from 1,761 · score 2.77
58.cwida / fsst
Fast Static Symbol Table (FSST): efficient random-access string compression
+14 stars
from 536 · score 2.71
+13 stars
from 2,449 · score 2.64
60.shrec / UltrafastSecp256k1
Ultra high-performance secp256k1 ECC engine | Python, Node.js, Rust, Go, C#, Swift, Java bindings | CUDA, Metal, OpenCL GPU | ECDSA, Schnorr, FROST, MuSig2, BIP-352 | 15+ platforms
- cryptography
- cuda
- riscv
- secp256k1
- arm64
- opencl
- +14 more
+13 stars
from 48 · score 2.64
61.apple / turicreateArchived
Turi Create simplifies the development of custom machine learning models.
+12 stars
from 11,141 · score 2.56
+12 stars
from 2,225 · score 2.56
63.jianboqi / CSF
LiDAR point cloud ground filtering / segmentation (bare earth extraction) method based on cloth simulation
+12 stars
from 640 · score 2.56
64.flashlight / wav2letter
Facebook AI Research's Automatic Speech Recognition Toolkit
- wav2letter
- speech-recognition
- end-to-end
- deep-learning
- cpp
+10 stars
from 6,434 · score 2.40
65.tiny-dnn / tiny-dnn
header only, dependency-free deep learning framework in C++14
- c-plus-plus
- deep-learning
- machine-learning
- neural-network
+10 stars
from 6,018 · score 2.40
+9 stars
from 1,629 · score 2.30
67.hyye / lio-mapping
Implementation of Tightly Coupled 3D Lidar Inertial Odometry and Mapping (LIO-mapping)
- sensor-fusion
- slam
- mapping
- icra2019
+9 stars
from 1,025 · score 2.30
68.Yixin-Hu / TetWild
Robust Tetrahedral Meshing in the Wild.
- geometry-processing
- tetrahedral-meshing
- surface-repair
- 3d-triangulation
+9 stars
from 715 · score 2.30
+9 stars
from 644 · score 2.30
70.shogun-toolbox / shogun
Shōgun
- machine-learning
- data-science
- artificial-intelligence
- swig
- c-plus-plus
- cmake
+8 stars
from 3,076 · score 2.20
71.gvinciguerra / PGM-index
🏅State-of-the-art learned data structure that enables fast lookup, predecessor, range searches and updates in arrays of billions of items using orders of magnitude less space than traditional indexes
- data-structures
- database
- cpp
- research
- indexing
- big-data
- +8 more
+8 stars
from 871 · score 2.20
72.PRBonn / semantic_suma
SuMa++: Efficient LiDAR-based Semantic SLAM (Chen et al IROS 2019)
- rangenet-lib
- suma
- lidar
- slam
- semantic
- 3d-lidar
- +1 more
+7 stars
from 1,012 · score 2.08
73.eyalroz / cuda-api-wrappers
Thin, unified, C++-flavored wrappers for the CUDA APIs
+7 stars
from 899 · score 2.08
74.meta-toolkit / meta
A Modern C++ Data Sciences Toolkit
- nlp
- nlp-parsing
- search-engine
- inverted-index
- pos-tag
- text-analysis
- +6 more
+7 stars
from 714 · score 2.08
75.Xtra-Computing / thundersvm
ThunderSVM: A Fast SVM Library on GPUs and CPUs
+6 stars
from 1,621 · score 1.95
76.yangjiaolong / Go-ICP
Implementation of the Go-ICP algorithm for globally optimal 3D pointset registration
+6 stars
from 504 · score 1.95
77.libfann / fann
Official github repository for Fast Artificial Neural Network Library (FANN)
- fann
- c
- neural-network
- library
+5 stars
from 1,743 · score 1.79
78.HKUST-Aerial-Robotics / ESVO
This repository maintains the implementation of "Event-based Stereo Visual Odometry".
+5 stars
from 503 · score 1.79
79.Dobiasd / frugally-deep
A lightweight header-only library for using Keras (TensorFlow) models in C++.
- tensorflow
- deep-learning
- keras
- cpp
- cpp14
- header-only
- +10 more
+4 stars
from 1,125 · score 1.61
80.Tessil / hat-trie
C++ implementation of a fast and memory efficient HAT-trie
- cpp
- trie
- hat-trie
- data-structures
- header-only
- c-plus-plus
+4 stars
from 871 · score 1.61
+4 stars
from 813 · score 1.61
82.PRBonn / rangenet_lib
Inference module for RangeNet++ (milioto2019iros, chen2019iros)
+4 stars
from 358 · score 1.61
83.strayrobots / 3d-annotation-tool
A graphical user interface to annotate point clouds and 3D data.
- point-cloud
- lidar
- computer-vision
- cpp
- detection
- 3d-vision
- +2 more
+4 stars
from 90 · score 1.61
84.aksnzhy / xlearn
High performance, easy-to-use, and scalable machine learning (ML) package, including linear model (LR), factorization machines (FM), and field-aware factorization machines (FFM) for Python and CLI interface.
- machine-learning
- statistics
- data-science
- data-analysis
- factorization-machines
- ffm
- +1 more
+3 stars
from 3,087 · score 1.39
85.NVIDIA / libcudacxxArchived
[ARCHIVED] The C++ Standard Library for your entire system. See https://github.com/NVIDIA/cccl
+3 stars
from 2,297 · score 1.39
86.msracver / Deep-Image-Analogy
The source code of 'Visual Attribute Transfer through Deep Image Analogy'.
- style-transfer
- deep-learning
+3 stars
from 1,365 · score 1.39
+3 stars
from 704 · score 1.39
+3 stars
from 580 · score 1.39
89.tensorflow / tflite-support
TFLite Support is a toolkit that helps users to develop ML and deploy TFLite models onto mobile / ioT devices.
+3 stars
from 438 · score 1.39
90.jkk-research / urban_road_filter
Real-time LIDAR-based Urban Road and Sidewalk detection for Autonomous Vehicles 🚗
- road-segmentation
- lidar
- point-cloud
- ros
- filter
- lidar-filter
- +8 more
+3 stars
from 356 · score 1.39
91.gagolews / stringi
Fast and Portable Character String Processing in R (with the Unicode ICU)
+3 stars
from 318 · score 1.39
92.wildmeshing / TriWild
TriWild: Robust Triangulation with Curve Constraints
- traingulation
- meshing
- geometry-processing
+3 stars
from 262 · score 1.39
93.apache / mxnetArchived
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
- mxnet
+2 stars
from 20,791 · score 1.10
+2 stars
from 885 · score 1.10
95.Xtra-Computing / thundergbm
ThunderGBM: Fast GBDTs and Random Forests on GPUs
- cuda
- gpu
- gbdt
- random-forest
- machine-learning
+2 stars
from 714 · score 1.10
96.niessner / VoxelHashing
[Siggraph Asia 2013] Large-Scale, Real-Time 3D Reconstruction
- 3d-reconstruction
- kinect
- computer-vision
+2 stars
from 709 · score 1.10
97.uxlfoundation / oneDAL
oneAPI Data Analytics Library (oneDAL)
- onedal
- data-analysis
- oneapi
- machine-learning
- machine-learning-algorithms
- hacktoberfest
- +8 more
+2 stars
from 651 · score 1.10
98.UMich-BipedLab / LiDARTag
This is a package for LiDARTag, described in paper: LiDARTag: A Real-Time Fiducial Tag System for Point Clouds
- fiducial-markers
- lidar
- point-clouds
- cassie
- robotics
- calibration
- +6 more
+2 stars
from 284 · score 1.10
99.tractatus / wholebrain
R package for segmentation, registration and generating web-based brain atlases from microscope images
+2 stars
from 92 · score 1.10
100.amazon-archives / amazon-dsstneArchived
Deep Scalable Sparse Tensor Network Engine (DSSTNE) is an Amazon developed library for building Deep Learning (DL) machine learning (ML) models
+1 stars
from 4,386 · score 0.69